Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals

摘要

Interpretability research aims to bridge the gap between the empirical success and our scientific understanding of the inner workings of large language models (LLMs). However, most existing research in this area focused on analyzing a single mechanism, such as how models copy or recall factual knowledge. In this work, we propose the formulation of competition of mechanisms, which instead of individual mechanisms focuses on the interplay of multiple mechanisms, and traces how one of them becomes dominant in the final prediction. We uncover how and where the competition of mechanisms happens within LLMs using two interpretability methods, logit inspection and attention modification. Our findings show traces of the mechanisms and their competition across various model components, and reveal attention positions that effectively control the strength of certain mechanisms.